University of Texas MD Anderson Cancer Center, Houston, TX.
PathomIQ Inc, Cupertini, CA.
JCO Clin Cancer Inform. 2023 Mar;7:e2200181. doi: 10.1200/CCI.22.00181.
Achieving a pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) is associated with improved patient outcomes in triple-negative breast cancer (TNBC). Currently, there are no validated predictive biomarkers for the response to NAC in TNBC. We developed and validated a deep convolutional neural network-based artificial intelligence (AI) model to predict the response of TNBC to NAC.
Whole-slide images (WSIs) of hematoxylin and eosin-stained core biopsies from 165 (pCR in 60 and non-pCR in 105) and 78 (pCR in 31 and non-pCR in 47) patients with TNBC were used to train and validate the model. The model extracts morphometric features from WSIs in an unsupervised manner, thereby generating clusters of morphologically similar patterns. Downstream ranking of clusters provided regions of interest and morphometric scores; a low score close to zero and a high score close to one represented a high or low probability of response to NAC.
The predictive ability of AI score for the entire cohort of 78 patients with TNBC ascertained by receiver operating characteristic analysis demonstrated an area under the curve (AUC) of 0.75. The AUC for stages I, II, and III disease were 0.88, 0.73, and 0.74, respectively. Using a cutoff value of 0.35, the positive predictive value of the AI score for pCR was 73.7%, and the negative predictive value was 76.2% for non-pCR patients.
To our knowledge, this study is the first to demonstrate the use of an AI tool on digitized hematoxylin and eosin-stained tissue images to predict the response to NAC in patients with TNBC with high accuracy. If validated in subsequent studies, these results may serve as an ancillary aid for individualized therapeutic decisions in patients with TNBC.
新辅助化疗（NAC）后获得病理完全缓解（pCR）与三阴性乳腺癌（TNBC）患者的预后改善相关。目前，TNBC 对 NAC 反应的预测生物标志物尚未得到验证。我们开发并验证了一种基于深度卷积神经网络的人工智能（AI）模型，以预测 TNBC 对 NAC 的反应。
使用 165 例（pCR 为 60 例，非 pCR 为 105 例）和 78 例（pCR 为 31 例，非 pCR 为 47 例）TNBC 患者的苏木精和伊红染色核心活检的全切片图像（WSI）来训练和验证该模型。该模型以非监督的方式从 WSI 中提取形态计量学特征，从而生成形态相似模式的聚类。下游聚类排名提供了感兴趣区域和形态计量学评分；接近零的低评分和接近一的高评分表示对 NAC 的高或低反应概率。
通过接受者操作特征分析确定的 78 例 TNBC 患者整个队列的 AI 评分预测能力显示曲线下面积（AUC）为 0.75。I 期、II 期和 III 期疾病的 AUC 分别为 0.88、0.73 和 0.74。使用 0.35 的截断值，AI 评分对 pCR 的阳性预测值为 73.7%，非 pCR 患者的阴性预测值为 76.2%。
据我们所知，这是第一项在数字化苏木精和伊红染色组织图像上使用 AI 工具预测 TNBC 患者对 NAC 反应的研究，具有很高的准确性。如果在后续研究中得到验证，这些结果可能成为 TNBC 患者个体化治疗决策的辅助手段。
